ATE247849T1 - METHOD FOR VERIFYING AN IMAGE OF A PRE-TRAINED NEURONAL NETWORK FOR USE IN SAFETY-CRITICAL SOFTWARE - Google Patents
METHOD FOR VERIFYING AN IMAGE OF A PRE-TRAINED NEURONAL NETWORK FOR USE IN SAFETY-CRITICAL SOFTWAREInfo
- Publication number
- ATE247849T1 ATE247849T1 AT00989262T AT00989262T ATE247849T1 AT E247849 T1 ATE247849 T1 AT E247849T1 AT 00989262 T AT00989262 T AT 00989262T AT 00989262 T AT00989262 T AT 00989262T AT E247849 T1 ATE247849 T1 AT E247849T1
- Authority
- AT
- Austria
- Prior art keywords
- look
- software
- trained
- case
- verifying
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3604—Software analysis for verifying properties of programs
- G06F11/3608—Software analysis for verifying properties of programs using formal methods, e.g. model checking, abstract interpretation
Abstract
A method of verifying pretrained, static, feedforward neural network mapping software using Lipschitz constants for determining bounds on output values and estimation errors is disclosed. By way of example, two cases of interest from the point of view of safety-critical software, like aircraft fuel gauging systems, are discussed. The first case is the simpler case of when neural net mapping software is trained to replace look-up table mapping software. A detailed verification procedure is provided to establish functional equivalence of the neural net and look-up table mapping functions on the entire range of inputs accepted by the look-up table mapping function. The second case is when a neural net is trained to estimate the quantity of interest form the process (such as fuel mass, for example) from redundant and noisy sensor signals. Given upper and lower bounds on sensor noises and on modeling inaccuracies, it is demonstrated how to verify the performance of such a neural network estimator (a "black box") when compared to a true value of the estimated quantity.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/465,881 US6473746B1 (en) | 1999-12-16 | 1999-12-16 | Method of verifying pretrained neural net mapping for use in safety-critical software |
PCT/US2000/033947 WO2001044939A2 (en) | 1999-12-16 | 2000-12-14 | Method of verifying pretrained neural net mapping for use in safety-critical software |
Publications (1)
Publication Number | Publication Date |
---|---|
ATE247849T1 true ATE247849T1 (en) | 2003-09-15 |
Family
ID=23849551
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AT00989262T ATE247849T1 (en) | 1999-12-16 | 2000-12-14 | METHOD FOR VERIFYING AN IMAGE OF A PRE-TRAINED NEURONAL NETWORK FOR USE IN SAFETY-CRITICAL SOFTWARE |
Country Status (5)
Country | Link |
---|---|
US (1) | US6473746B1 (en) |
EP (1) | EP1250648B1 (en) |
AT (1) | ATE247849T1 (en) |
DE (1) | DE60004709T2 (en) |
WO (1) | WO2001044939A2 (en) |
Families Citing this family (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
IL113913A (en) * | 1995-05-30 | 2000-02-29 | Friendly Machines Ltd | Navigation method and system |
DE10201018B4 (en) * | 2002-01-11 | 2004-08-05 | Eads Deutschland Gmbh | Neural network, optimization method for setting the connection weights of a neural network and analysis methods for monitoring an optimization method |
DE10225343A1 (en) * | 2002-06-06 | 2003-12-18 | Abb Research Ltd | Spurious measurement value detection method uses wavelet functions in defining a reporting window for rejecting spurious values in a continuous digital sequence of measurement values |
US7203716B2 (en) * | 2002-11-25 | 2007-04-10 | Simmonds Precision Products, Inc. | Method and apparatus for fast interpolation of multi-dimensional functions with non-rectangular data sets |
US7296006B2 (en) * | 2002-11-25 | 2007-11-13 | Simmonds Precision Products, Inc. | Method of inferring rotorcraft gross weight |
US7937343B2 (en) | 2003-03-28 | 2011-05-03 | Simmonds Precision Products, Inc. | Method and apparatus for randomized verification of neural nets |
US8689194B1 (en) | 2007-08-20 | 2014-04-01 | The Mathworks, Inc. | Optimization identification |
US8775341B1 (en) | 2010-10-26 | 2014-07-08 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
US9015093B1 (en) | 2010-10-26 | 2015-04-21 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
CN102567137B (en) * | 2010-12-27 | 2013-09-25 | 北京国睿中数科技股份有限公司 | System and method for restoring contents of RAT (register alias table) by using ROB (reorder buffer) when branch prediction fails |
DE102017205093A1 (en) | 2017-03-27 | 2018-09-27 | Conti Temic Microelectronic Gmbh | Method and system for predicting sensor signals of a vehicle |
DE102017212328A1 (en) | 2017-07-19 | 2019-01-24 | Robert Bosch Gmbh | Function monitoring for AI modules |
DE102017212839A1 (en) | 2017-07-26 | 2019-01-31 | Robert Bosch Gmbh | Control Module for Artificial Intelligence |
WO2019241775A1 (en) * | 2018-06-15 | 2019-12-19 | Insurance Services Office, Inc. | Systems and methods for optimized computer vision using deep neural networks and lipschitz analysis |
US11501164B2 (en) | 2018-08-09 | 2022-11-15 | D5Ai Llc | Companion analysis network in deep learning |
CN109409431B (en) * | 2018-10-29 | 2020-10-09 | 吉林大学 | Multi-sensor attitude data fusion method and system based on neural network |
CN109598815A (en) * | 2018-12-04 | 2019-04-09 | 中国航空无线电电子研究所 | A kind of estimation of Fuel On Board system oil consumption and health monitor method |
US11693373B2 (en) * | 2018-12-10 | 2023-07-04 | California Institute Of Technology | Systems and methods for robust learning-based control during forward and landing flight under uncertain conditions |
US11625487B2 (en) | 2019-01-24 | 2023-04-11 | International Business Machines Corporation | Framework for certifying a lower bound on a robustness level of convolutional neural networks |
US11625554B2 (en) | 2019-02-04 | 2023-04-11 | International Business Machines Corporation | L2-nonexpansive neural networks |
US11521014B2 (en) | 2019-02-04 | 2022-12-06 | International Business Machines Corporation | L2-nonexpansive neural networks |
-
1999
- 1999-12-16 US US09/465,881 patent/US6473746B1/en not_active Expired - Lifetime
-
2000
- 2000-12-14 DE DE60004709T patent/DE60004709T2/en not_active Expired - Fee Related
- 2000-12-14 AT AT00989262T patent/ATE247849T1/en not_active IP Right Cessation
- 2000-12-14 EP EP00989262A patent/EP1250648B1/en not_active Expired - Lifetime
- 2000-12-14 WO PCT/US2000/033947 patent/WO2001044939A2/en active IP Right Grant
Also Published As
Publication number | Publication date |
---|---|
US6473746B1 (en) | 2002-10-29 |
WO2001044939A3 (en) | 2002-08-15 |
EP1250648A2 (en) | 2002-10-23 |
DE60004709T2 (en) | 2004-06-17 |
WO2001044939A2 (en) | 2001-06-21 |
EP1250648B1 (en) | 2003-08-20 |
DE60004709D1 (en) | 2003-09-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
ATE247849T1 (en) | METHOD FOR VERIFYING AN IMAGE OF A PRE-TRAINED NEURONAL NETWORK FOR USE IN SAFETY-CRITICAL SOFTWARE | |
Koh et al. | Identification and uncertainty estimation of structural parameters | |
Trémolet | Incremental 4D-Var convergence study | |
Locascio | The cross-lagged correlation technique: Reconsideration in terms of exploratory utility, assumption specification and robustness | |
Faust | Near observational equivalence and theoretical size problems with unit root tests | |
Bauer et al. | Assimilation of wave data into the wave model WAM using an impulse response function method | |
CN110207721A (en) | A kind of invalid landform matching result recognition methods considering residual distribution | |
Aguirre et al. | Cluster analysis of NARMAX models for signal-dependent systems | |
Giarre et al. | SM identification of approximating models for H/sub/spl infin//robust control | |
Steger | Analytical and empirical performance evaluation of subpixel line and edge detection | |
CN105678716A (en) | Correction method and apparatus for atmospheric interference phase in ground-based SAR | |
Falk et al. | Remarks on mixed finite element methods for problems with rough coefficients | |
Holcomb | A numerical study of some potential sources of error in side-by-side seismometer evaluations | |
Csanady | Shelf circulation cells | |
Roşu et al. | Certifying optimality of state estimation programs | |
Peyton Jones et al. | Mean levels in nonlinear analysis and identification | |
US6271789B1 (en) | Method for checking the reliability of nominal position indications | |
Borisov | On the rate of convergence of distributions of functionals of integral type | |
Kim | Real-time Monitoring by Using Kalman Filter in the Ocean | |
Tomlinson et al. | Hilbert transform procedures for detecting and quantifying non-linearity in modal testing | |
Cardona-Morales et al. | Instantaneous frequency estimation and order tracking based on Kalman filters | |
Germani et al. | Kalman-Bucy filtering for singular stochastic differential systems | |
Palmerio | Coupling mesh and flow in viscous fluid calculations on unstructured triangular finite elements | |
Giarrè et al. | SM identification of approximating models for H∞ robust control | |
Wu et al. | Research on dynamic calibration technology of shock accelerometer based on model method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
RER | Ceased as to paragraph 5 lit. 3 law introducing patent treaties |